claude

prompt-coach

Uplevel prompts with the right guardrails, verify AI answers before they ship, teach staff to prompt better, and keep the guidance current via a human-approved refresh cycle.

1 on GitHubby Lauren Townsendv0.3.1MITupdated 18 days agoproductivity
/

Plugin prompt-coach from marketplace townsend-plugins in laurenbdaniels-coder/townsend-plugins. Commands read from the repo's manifest — 13 days ago.

What it installs

Skills (4)

  • check-answer

    Runs a verification battery on an existing AI-generated answer, draft, or multi-file package — claim-by-claim audit, citation check, premise check, math recomputation, fold test, and a provenance-and-audience sweep — and returns a "verify before use" list plus a "strip before send" list. Use wheneve

  • coach

    Teaches prompting skills interactively — short lessons, before/after examples in nonprofit contexts, and practice exercises with feedback. Use whenever the user asks to learn prompting, get better at prompts, understand why a prompt works, or train on AI guardrails; says "teach me", "give me a promp

  • refresh

    Researches current best practices for prompting, AI guardrails, and hallucination prevention from trusted sources, then proposes updates to the Prompt Coach knowledge base and applies them only after explicit user approval. Use whenever the user asks to refresh, update, audit, or check the currency

  • uplevel

    Rewrites a draft prompt with the right guardrails for its task type and stakes, then teaches the user why each change was made. Use whenever the user asks to uplevel, improve, strengthen, fix, review, or coach a prompt; says "make this prompt better", "how should I ask this", "what's wrong with my p

View source on GitHub

More from laurenbdaniels-coder/townsend-plugins

All 7 plugins →

Stage-by-stage product management workflow: discovery, positioning, strategy, prioritization, PRD, delivery, launch, and measurement — with framework menus, fill-in templates with quality bars, evidence rules, a shared project workspace, and a built-in critique gate.

10 skills

1

Run the eleven gut-check questions from 'It Said It Was Fine' on your own AI-built app, read-only, and get a plain report: what is broken, what it means for you, and what your code can't tell. Works in Claude Code and Codex.

1 skill · 1 agent · hooks

1

Shows where your AI-built app decides the same thing twice (who sees what, what things cost, who has paid, how money rounds), what each one means for you, and how the app is built. It also warns, on its own, when your app does one job with two or more libraries, or when a JavaScript app lists parts it does not use. Read-only; a review, not an audit.

1 skill

1

Decision Census is now Build Decisions. This pointer tells you how to install build-decisions and remove this plugin. It runs nothing.

1 skill

1

A self-development coach for product managers: competency baseline against a behavioral rubric, growth plan with weekly deliberate-practice reps, and evidence-based progress tracking using your real work artifacts.

1 skill

1

When Claude stops to ask you a technical yes/no or choice, it spells it out first: the ask, where things stand, what each answer changes, whether you can undo it, its pick, the safe answer if you're not sure, and a one-line TL;DR. For people who build with AI but don't read code.

1 skill

1

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain prompt-coach?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins7 plugins